首页 | 本学科首页   官方微博 | 高级检索  
     

基于近红外光谱技术的海参品质快速检测
引用本文:邹小波,薛 瑾,石吉勇,徐艺伟,翟晓东,胡雪桃,崔雪平.基于近红外光谱技术的海参品质快速检测[J].食品安全质量检测技术,2017,8(9):3431-3437.
作者姓名:邹小波  薛 瑾  石吉勇  徐艺伟  翟晓东  胡雪桃  崔雪平
作者单位:江苏大学食品与生物工程学院,江苏大学食品与生物工程学院,江苏大学食品与生物工程学院,江苏大学食品与生物工程学院,江苏大学食品与生物工程学院,江苏大学食品与生物工程学院,江苏大学食品与生物工程学院
基金项目:国家自然科学基金项目(31671844)、国家科技支撑项目(2015BAD17B04)、“十三五”国家重点研发计划项目(2016YFD0401104)、江苏省自然科学基金项目(BK20160506)
摘    要:目的应用近红外光谱技术建立海参产地区分和胶原蛋白快速检测的方法。方法总计43个海参样品来自大连、福建、连云港、山东4个地区。首先采集样品的近红外光谱图,经过标准正态变量(standard normal variables,SNV)预处理,利用不同定性判别模型对海参产地进行区分。通过分光光度计法测定海参的胶原蛋白含量,利用偏最小二乘法(partial least squares,PLS)、区间偏最小二乘法(interval partial least squares,iPLS)、向后区间偏最小二乘法(backwards interval partial least squares,BiPLS)和联合区间偏最小二乘法(synergy interval partial least squares,Si PLS)建立了海参胶原蛋白含量的预测模型。结果产地区分模型中最小二乘支持向量机(least-squares support vector machine regression,LS-SVM)的识别率最高,校正集识别率为100%,预测集识别率为95.35%;海参胶原蛋白预测模型中BiPLS的预测效果较好,校正集相关系数Rc为0.9002,预测集相关系数Rp为0.8517。结论近红外光谱技术可实现对海参的产地区分和胶原蛋白的快速检测。

关 键 词:海参    产地区分    近红外光谱分析技术    胶原蛋白    向后区间偏最小二乘法    最小二乘支持向量机
收稿时间:2017/6/30 0:00:00
修稿时间:2017/8/16 0:00:00

Rapid determination of sea cucumber quality based on near-infrared spectroscopy
ZOU Xiao-Bo,XUE Jin,SHI Ji-Yong,XU Yi-Wei,ZHAI Xiao-Dong,HU Xue-Tao and CUI Xue-Ping.Rapid determination of sea cucumber quality based on near-infrared spectroscopy[J].Food Safety and Quality Detection Technology,2017,8(9):3431-3437.
Authors:ZOU Xiao-Bo  XUE Jin  SHI Ji-Yong  XU Yi-Wei  ZHAI Xiao-Dong  HU Xue-Tao and CUI Xue-Ping
Affiliation:School of Food and Biological Engineering, Jiangsu University,School of Food and Biological Engineering, Jiangsu University,School of Food and Biological Engineering, Jiangsu University,School of Food and Biological Engineering, Jiangsu University,School of Food and Biological Engineering, Jiangsu University,School of Food and Biological Engineering, Jiangsu University and School of Food and Biological Engineering, Jiangsu University
Abstract:Objective To establish a method for determination of collagen content of sea cucumber from different geographical origins by near-infrared spectroscopy (NIR). Methods Forty-three sea cucumber samples were collected from Dalian, Fujian, Lianyungang and Shandong. Near-infrared spectra of the samples were collected and pretreated by standard normal variables (SNV). Then, the geographical origin of the sea cucumber was determined by using qualitative discriminant models based on the pretreated spectra. The collagen content of sea cucumber was determined with UV spectrophotometry. Partial least squares (PLS), interval partial least squares (iPLS), backwards interval partial least squares (BiPLS) and synergy interval partial least squares (SiPLS) were used to build quantitive prediction models for the collagen content. Results The optimal qualitative discriminant model for the geographical origins of sea cucumber was least-squares support vector machine regression (LS-SVM), and its recognition rates of calibration set and prediction set were 100% and 95.35%, respectively. The best quantitive prediction model for collagen content was BiPLS, and its calibration coefficient (Rc) and prediction coefficient (Rp) were 0.9002 and 0.8517, respectively. Conclusion Near-infrared spectroscopy can be used to rapidly determine the geographical origins and the collagen content of sea cucumber.
Keywords:sea cucumber  geographical origins identification  near-infrared spectroscopy  collagen  backwards interval partial least squares  least-squares support vector machine regression
本文献已被 CNKI 等数据库收录!
点击此处可从《食品安全质量检测技术》浏览原始摘要信息
点击此处可从《食品安全质量检测技术》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号